基于STSSA-PID神经网络多变量解耦控制器优化  

Optimization of Multivariable Decoupling Controller Based on STSSA-PID Neural Network

作　　者：凌胜 LING Sheng(School of Mechanics and Optoelectronic Physics,Anhui University of Science and Technology,Huainan Anhui 232001,China)

机构地区：[1]安徽理工大学力学光电物理学院,安徽淮南232001

出　　处：《佳木斯大学学报（自然科学版）》2023年第3期16-19,74,共5页Journal of Jiamusi University：Natural Science Edition

摘　　要：由于传统PID神经网络多变量解耦控制器在实际过程中出现超调量较大和调节时间较长的现象。设计出一种基于融合T分布策略的麻雀搜索算法PID神经网络解耦智能控制算法(STSSA-PID神经网络控制器算法)。针对PID神经元网络解耦控制器算法利用梯度学习法。由于权值随机的,权值在利用梯度学习过程中网络权值会得到局部最优解问题。因此,利用改进的麻雀搜索算法优化神经元网络权值,使其获得全局最优权值。在实验中通过比较PID,SSA-PID以及STSSA-PID神经网络三种控制器仿真结果,结果表明改进算法可以提高PID神经网络解耦控制器的收敛性速度,较大提高了调节精度,缩短调节时间。The traditional PID neural network multivariable decoupling controller has a large overshoot and a long adjustment time in the actual process.This paper designs a sparrow search algorithm PID neural network decoupling intelligent control algorithm(STSSA-PID neural network controller algorithm)based on the fusion T-distribution strategy.For PID neural network decoupling controller algorithm using gradient learning method,there is the problem that the network weight will get the local optimal solution in the process of using gradient learning because the initial weight of the network is random.Therefore,the improved sparrow search algorithm is used to optimize the weight of the neural network to obtain the global optimal weight.In the experiment,by comparing the simulation results of PID,SSA-PID and STSSA-PID neural network controller,the results show that the improved algorithm can improve the convergence speed of PID neural network decoupling controller,greatly improve the adjustment accuracy and shorten the adjustment time.

关 键 词：PID神经网络 解耦控制 麻雀搜索算法 T分布策略 

分 类 号：TN911.73[电子电信—通信与信息系统]